Skip to main content
skill CX Codex

critique-typography — Claude Code skill: audit screen typography

Audits typography on a rendered screen: scale usage, readability, consistency and token compliance. Useful during UI review.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Owl-Listener/designer-skills --skill critique-typography -a claude-code
Open on GitHub

What critique-typography does

The skill reviews every typographic decision on a screen across four dimensions. Scale usage: whether only defined steps are used (display, h1–h4, body-lg, body-sm, caption) and whether arbitrary sizes sit outside the system. Readability: minimum text sizes, line-height matched to content type, line length, letter-spacing and WCAG AA contrast. Consistency: whether equivalent elements share one style, whether alignment is mixed, whether one-off treatments exist. Token compliance: whether font-family, font-size, font-weight, line-height and letter-spacing come from tokens or raw values.

For each dimension you get an observation, the problem and a specific fix, plus a rating of pass, minor issue or major issue. Non-compliant values are listed with the correct token name, which makes the output easy to hand off.

It works on a screen that already exists, not on building a scale from scratch. For defining the scale itself, the description points to typography-scale from the ui-design set. Worth installing when the type is already rendered and you want it checked.

What it helps with

  • spot font sizes that fall outside the defined scale
  • check text and background contrast against WCAG AA
  • unify equivalent elements under one type style
  • swap hardcoded values for typography tokens
  • catch mixed alignment and stray font weights

Example prompts for the agent

  • critique the typography on this screen and give me fixes per dimension
  • find hardcoded font-size values in these components and name the right tokens
  • review readability on the mobile layout: sizes, line-height, measure

How to install critique-typography

1Skills CLI (Vercel)

npx skills add Owl-Listener/designer-skills --skill critique-typography -a claude-code

2Manually: put the files in place

~/.claude/skills/critique-typography/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/critique-typography/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about critique-typography

How do I install critique-typography in Claude?

Run npx skills add Owl-Listener/designer-skills --skill critique-typography -a claude-code. The skill lands in ~/.claude/skills/critique-typography/SKILL.md.

What does critique-typography do?

It audits typography on a rendered screen across scale, readability, consistency and token compliance. Each dimension comes back with an observation, a problem and a fix.

How is it different from typography-scale?

critique-typography reviews a finished screen. For defining the scale itself, the description points to typography-scale from the ui-design set.

Source text

SKILL.md · MIT
---
name: critique-typography
description: Critique a rendered screen's typography — scale usage, readability, consistency, and token compliance. Use when reviewing type on a screen. For defining the scale itself, use `typography-scale` (ui-design).
---
# Critique Typography
You are an expert in typographic systems and screen-level type critique.
## What You Do
You audit all typographic decisions on a screen: whether the type scale is applied correctly, whether text is readable at its context, whether type choices are consistent across the view, and whether design tokens are used in place of raw values. You flag problems and provide specific fixes.
## Critique Dimensions
### Scale Usage
Evaluate whether the type scale is applied as a system, not ad hoc.
- Are only defined scale steps used (e.g., display, h1–h4, body-lg, body-sm, caption)?
- Is each scale step used for its intended purpose — headings as headings, labels as labels?
- Are intermediate or arbitrary sizes present that fall outside the defined scale?
- Does the scale create sufficient contrast between hierarchy levels (recommend ≥1.25× ratio per step)?
### Readability
Evaluate whether text can be read comfortably in its context.
- Do body text sizes meet minimum thresholds (16px / 1rem on desktop; 14px on mobile minimum)?
- Is line-height set for the content type: tighter for headings (1.1–1.3), looser for body (1.4–1.6)?
- Is line length (measure) within 45–75 characters for body copy?
- Is letter-spacing appropriate — not over-tracked or compressed to the point of friction?
- Is contrast ratio between text and background WCAG AA compliant (4.5:1 body, 3:1 large text)?
### Consistency
Evaluate whether type decisions are uniform across the screen.
- Do semantically equivalent elements (e.g., all card titles, all form labels) use the same type style?
- Are alignment choices consistent — left, centre, or right applied with intention and not mixed randomly?
- Are font weights used consistently and not randomly varied (e.g., some labels bold, others regular)?
- Are there orphaned styles — one-off type treatments not used elsewhere?
### Token Compliance
Evaluate whether typography tokens are applied instead of raw values.
- Are font-family, font-size, font-weight, line-height, and letter-spacing set via tokens?
- Are any hardcoded CSS or design property values present that should reference a token?
- List every non-compliant value with its correct token name.
## Output Format
For each dimension — Scale, Readability, Consistency, Token Compliance — provide:
1. **Observation** — what you see (neutral, factual)
2. **Problem** — what is broken and why it matters
3. **Fix** — a specific, actionable change (including correct token name where applicable)
Rate each dimension: `pass` / `minor issue` / `major issue`.
## Common Failure Patterns
- Scale drift — designers nudging sizes by 1–2px instead of moving to the next defined step
- Line-height mismatches — display sizes with body line-height and vice versa
- Alignment mixing — centred headings above left-aligned body text without intentional justification
- Hardcoded font-size values in components because the token was not found or not updated
- Over-use of bold — more than two weight levels active on a single screen dilutes contrast

© Owl-Listener · MIT · Owl-Listener/designer-skills

Similar skills

Everything for Design →

From the same set109

component-spec This skill writes a full spec for one design-system component: anatomy, variants, states, accessibility and usage rules. Useful when a library grows and the API needs pinning down. CX Codex +1 2,100installs design-principles Helps teams define actionable design principles to resolve recurring product debates. Useful when the same decisions keep getting relitigated. CX Codex +1 2,100installs accessibility-audit Audits an existing interface against WCAG and reports issues with severity, impact, and remediation steps. CX Codex +1 2,100installs ux-writing Writes microcopy, error messages, empty states and CTAs. Useful when the words themselves are the deliverable. CX Codex +1 2,200installs version-control-strategy Defines version control strategies for design files, component libraries, and tokens. It helps teams stop chaotic file history and establish clear release routines. CX Codex +1 2,000installs critique-visual-hierarchy This skill reviews a rendered screen across four dimensions and tells you where the eye actually lands. Useful when attention goes to the wrong place. CX Codex +1 2,000installs click-test-plan Turns a findability question into a test plan: where users click first and whether they locate items in your navigation. Useful when a design is ready but untested. CX Codex +1 2,000installs design-sprint-plan Plans structured design sprints to move from a challenge statement to a tested prototype in days. Ideal when you need to compress discovery work into a single week. CX Codex +1 2,000installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor